Struct SimHashDocumentEncoder 

pub struct SimHashDocumentEncoder { /* private fields */ }

SimHash Document Encoder.

Encodes documents and text into SDRs where similar documents will have similar representations. Uses the SimHash algorithm with SHA3/SHAKE256 hashing.

Example

use mokosh::encoders::{SimHashDocumentEncoder, SimHashDocumentEncoderParams, Encoder};

let encoder = SimHashDocumentEncoder::new(SimHashDocumentEncoderParams {
    size: 400,
    active_bits: 21,
    ..Default::default()
}).unwrap();

let tokens = vec!["hello".to_string(), "world".to_string()];
let sdr = encoder.encode_to_sdr(tokens).unwrap();
assert_eq!(sdr.get_sum(), 21);

Implementations

impl SimHashDocumentEncoder

pub fn new(params: SimHashDocumentEncoderParams) -> Result<Self>

Creates a new SimHash Document Encoder.

pub fn size_param(&self) -> UInt

Returns the size.

pub fn active_bits(&self) -> UInt

Returns the number of active bits.

pub fn encode_tokens(&self, tokens: &[String], output: &mut Sdr) -> Result<()>

Encode a list of tokens.

pub fn encode_string(&self, input: &str, output: &mut Sdr) -> Result<()>

Encode a string by splitting on whitespace.

Trait Implementations

impl Clone for SimHashDocumentEncoder

fn clone(&self) -> SimHashDocumentEncoder

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for SimHashDocumentEncoder

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Encoder<&str> for SimHashDocumentEncoder

Convenience implementation for string slices.

fn dimensions(&self) -> &[UInt]

Returns the dimensions of the output SDR.

fn size(&self) -> usize

Returns the total size of the output SDR.

fn encode(&self, value: &str, output: &mut Sdr) -> Result<()>

Encodes a value into an SDR.

fn encode_to_sdr(&self, value: T) -> Result<Sdr>

Encodes a value and returns a new SDR.

impl Encoder<String> for SimHashDocumentEncoder

Convenience implementation for String.

fn dimensions(&self) -> &[UInt]

Returns the dimensions of the output SDR.

fn size(&self) -> usize

Returns the total size of the output SDR.

fn encode(&self, value: String, output: &mut Sdr) -> Result<()>

Encodes a value into an SDR.

fn encode_to_sdr(&self, value: T) -> Result<Sdr>

Encodes a value and returns a new SDR.

impl Encoder<Vec<String>> for SimHashDocumentEncoder

fn dimensions(&self) -> &[UInt]

Returns the dimensions of the output SDR.

fn size(&self) -> usize

Returns the total size of the output SDR.

fn encode(&self, value: Vec<String>, output: &mut Sdr) -> Result<()>

Encodes a value into an SDR.

fn encode_to_sdr(&self, value: T) -> Result<Sdr>

Encodes a value and returns a new SDR.